active-directory-attack-paths
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill describes a methodology that involves the agent ingesting and analyzing data from an Active Directory environment, which creates a potential surface for indirect prompt injection. 1. Ingestion points: The skill instructs the agent to process outputs from various system tools such as whoami, BloodHound, and mimikatz in SKILL.md. 2. Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions within these tool outputs. 3. Capability inventory: The skill suggests executing several powerful CLI tools including hashcat, mimikatz, and Certipy. 4. Sanitization: There are no instructions for validating or sanitizing the retrieved AD data before processing.
- [NO_CODE]: The skill consists entirely of markdown-based instructions and methodology; it does not distribute any executable scripts, binaries, or automated logic.
Audit Metadata